{"id":"https://openalex.org/W7204880698","doi":"https://doi.org/10.48550/arxiv.2608.28916","title":"VoiceCodeBench: Evaluating Exact Structured-Token Recovery in Automatic Speech Recognition","display_name":"VoiceCodeBench: Evaluating Exact Structured-Token Recovery in Automatic Speech Recognition","publication_year":2026,"publication_date":"2026-08-28","ids":{"openalex":"https://openalex.org/W7204880698","doi":"https://doi.org/10.48550/arxiv.2608.28916"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.28916","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28916","pdf_url":"https://arxiv.org/pdf/2608.28916","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.28916","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148936674","display_name":"Tyler Baumgartner","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baumgartner, Tyler","raw_affiliation_strings":["Besimple AI , San Mateo , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Besimple AI , San Mateo , CA , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148859141","display_name":"Brandon Tai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tai, Brandon","raw_affiliation_strings":["Besimple AI , San Mateo , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Besimple AI , San Mateo , CA , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148854442","display_name":"Lisa Kaelin-Martin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaelin-Martin, Lisa","raw_affiliation_strings":["Besimple AI , San Mateo , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Besimple AI , San Mateo , CA , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148849053","display_name":"Candice Fan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Candice","raw_affiliation_strings":["Besimple AI , San Mateo , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Besimple AI , San Mateo , CA , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148926588","display_name":"Luc Debaupte","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Debaupte, Luc","raw_affiliation_strings":["Besimple AI , San Mateo , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Besimple AI , San Mateo , CA , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062578433","display_name":"Bill Wang","orcid":"https://orcid.org/0000-0002-3504-8683","observed_orcids":["https://orcid.org/0000-0002-3504-8683"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Bill","raw_affiliation_strings":["Besimple AI , San Mateo , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Besimple AI , San Mateo , CA , USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148932965","display_name":"Yi Zhong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Yi","raw_affiliation_strings":["Besimple AI , San Mateo , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Besimple AI , San Mateo , CA , USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/workplace-talk","display_name":"workplace speech","score":0.3959999978542328},{"id":"https://openalex.org/keywords/entity-recognition","display_name":"entity recognition","score":0.43700000643730164},{"id":"https://openalex.org/keywords/task-success-rate","display_name":"task success rate","score":0.9459999799728394},{"id":"https://openalex.org/keywords/streaming-asr","display_name":"streaming ASR","score":0.4860000014305115}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6801000237464905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6777999997138977},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.590499997138977},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5770999789237976},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5710999965667725},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5648999810218811},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5601999759674072},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.5436000227928162},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.484499990940094},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4499000012874603},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4438999891281128},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.3846000134944916},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3375999927520752},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C204707403","wikidata":"https://www.wikidata.org/wiki/Q1152398","display_name":"Canonical form","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2572000026702881},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.28916","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28916","pdf_url":"https://arxiv.org/pdf/2608.28916","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.28916","doi":"https://doi.org/10.48550/arxiv.2608.28916","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.28916","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.28916","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28916","pdf_url":"https://arxiv.org/pdf/2608.28916","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204880698.pdf","grobid_xml":"https://content.openalex.org/works/W7204880698.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7131795327","https://openalex.org/W4402112216","https://openalex.org/W2798685342","https://openalex.org/W2565377570","https://openalex.org/W3132946990","https://openalex.org/W7214401718","https://openalex.org/W7221185710","https://openalex.org/W7100830330","https://openalex.org/W3012044729","https://openalex.org/W2404260248"],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"recognition":[2],"is":[3],"usually":[4],"evaluated":[5],"with":[6,87,113],"word":[7],"error":[8],"rate":[9],"(WER),":[10],"although":[11],"voice":[12],"workflows":[13],"often":[14],"require":[15],"exact":[16],"written":[17],"values.":[18],"VoiceCodeBench":[19],"measures":[20],"whether":[21],"transcripts":[22],"preserve":[23],"identifiers,":[24],"paths,":[25],"commands,":[26],"and":[27,46,53,64,73,97,101,120],"other":[28],"structured":[29],"tokens":[30],"needed":[31],"by":[32],"downstream":[33],"software.":[34],"It":[35],"contains":[36],"300":[37],"human-recorded":[38],"English":[39],"workplace":[40],"segments":[41],"(5.59":[42],"hours,":[43],"85":[44],"speakers)":[45],"1,482":[47],"audited":[48],"entities":[49,122],"across":[50],"26":[51],"types":[52],"eight":[54],"domains.":[55],"Under":[56],"a":[57],"raw-audio-only":[58],"protocol,":[59],"we":[60],"evaluate":[61],"19":[62],"batch":[63],"streaming":[65],"systems":[66],"using":[67],"WER,":[68],"Canonical":[69],"Token/Entity":[70],"Match":[71],"(CTEM),":[72],"strict":[74],"segment-level":[75],"Task":[76],"Success":[77],"Rate":[78],"(TSR).":[79],"Across":[80],"systems,":[81],"WER":[82],"has":[83],"little":[84],"rank":[85],"agreement":[86],"CTEM":[88,96],"(Spearman":[89],"$\u03c1=-0.28$)":[90],"or":[91],"TSR":[92,98],"($\u03c1=-0.22$).":[93],"The":[94],"best":[95],"are":[99],"91.8%":[100],"68.7%.":[102],"Even":[103],"the":[104],"strongest":[105],"system":[106],"therefore":[107],"leaves":[108],"nearly":[109],"one-third":[110],"of":[111],"recordings":[112],"an":[114],"unrecovered":[115],"critical":[116],"value.":[117],"Symbol-,":[118],"separator-,":[119],"boundary-sensitive":[121],"account":[123],"for":[124],"most":[125],"errors.":[126]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-02T00:00:00"}